Home
Short Bio
I am currently at Google Deepmind on the Vizier team and co-creator of OSS Vizier, working on hyperparameter optimization, Bayesian methods, and theoretical machine learning. I also dabble a bit in AI alignment, ethics and the intersection of Faith and AI.
I steward the Global Christians in AI (CHAI) community, where you can find many personal musings on Christianity and AI. I also organize talks and workshops at Google and academic conferences about related topics; please join the community if you would like to learn more!I am grateful to have graduated with a PhD in Applied Mathematics and Computer Science at UC Berkeley, where I was fortunate to be advised under Prof. Satish Rao and Prof. Nikhil Srivastava. My interests are in the intersection of optimization, theoretical computer science and machine learning. Previously, I graduated in the Great Class of 2014 from Princeton University.
Pre-prints and Talks
Belief-based AI Fairness
with Google Research.
Pre-print.
Papers
Robust Algorithms on Adaptive Inputs from Bounded Adversaries
with Yeshwanth Cherapanamjeri, Sandeep Silwal, David Woodruff, Fred Zhang, Samson Zhou.
ICLR 2023.Towards Learning Universal Hyperparameter Optimizers with Transformers
with Yutian Chen, Xingyou Song, Chansoo Lee, Zi Wang, David Dohan, Kazuya Kawakami, Greg Kochanski, Arnaud Doucet, Marc'aurelio Ranzato, Sagi Perel, Nando de Freitas.
Neurips 2022. [Google AI Blog]Optimal Query Complexities for Dynamic Trace Estimation
with David Woodruff, Fred Zhang.
Neurips 2022 (Spotlight).Leveraging Initial Hints for Free in Stochastic Linear Bandits
with Ashok Cutkosky, Chris Dann, Abhimanyu Das.
ALT 2022.Optimal Sketching for Trace Estimation
with Shuli Jiang, Hai Pham, David Woodruff.
Neurips 2021 (Spotlight).One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
with Atish Agarwala, Abhimanyu Das, Brendan Juba, Rina Panigrahy, Vatsal Sharan, Xin Wang.
ICLR 2021.Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
with Daniel Golovin.
ICML 2020.Gradientless Descent: High-Dimensional Zeroth-Order Optimization [slides]
with Daniel Golovin, John Karro, Greg Kochanski, Chansoo Lee, Xingyou Song.
ICLR 2020 (Spotlight).Span Recovery for Deep Neural Networks with Applications to Input Obfuscation
with Rajesh Jayaram, David Woodruff.
ICLR 2020.Regularized Weighted Low Rank Approximation
with Frank Ban, David Woodruff.
NEURIPS 2019.Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
with Zhao Song, Yin Tat Lee.
COLT 2019.Optimal Sequence Length Requirements for Phylogenetic Tree Reconstruction with Indels
with Arun Ganesh.
STOC 2019.Using INC Within Divide-and-Conquer Phylogeny Estimation
with Thien Le, Aaron Sy, Erin Molloy, Satish Rao, Tandy Warnow.
AlCoB 2019.New Absolute Fast Converging Phylogeny Estimation Methods with Improved Scalability and Accuracy
with Satish Rao, Tandy Warnow.
WABI 2018.Convergence Results for Neural Networks via Electrodynamics
with Rina Panigrahy, Sushant Sachdeva.
ITCS 2018.Forbidden Directed Minors and Kelly-width
with Shiva Kintali.
Theoretical Computer Science 2017, Vol. 662.
Contact
- Email: qiuyizhang (at) gmail (dot) com
- Office: Google Pittsburgh in Bakery Square